Call for applications | Postdoctoral position @ OpenCEMS Industrial Chair (deadline: June 25th, 2022)

Please, consider sharing this call for postdoc among colleagues, post-docs and last-year PhD students.

CONTEXT AND MAIN PURPOSE:

The Connected Environment & Distributed Energy Data Management Solutions (OpenCEMS) industrial chair addresses the issues that businesses and communities encounter when handling data management in their connected environments. The OpenCEMS research group aims at designing, implementing and deploying software solutions within Small and Large Scale Distributed/Connected Environments for better data collection/aggregation, information retrieval, and knowledge extraction.

DESCRIPTION OF THE POSTDOC ACTIVITIES:

This postdoctoral fellowship’s global objective is to design and develop hybrid information retrieval which uses the semantics of data (i.e., Ontologies, terminologies, dictionaries), community preferences as well as collaborative filtering techniques for semantic information retrieval. The idea is to improve the accuracy by applying topic modeling for the corpus rather than dealing with the documents as bag of words to capture the hidden relationships between the words in order to group words into specific topics, and then expand the query to explore and discovery hidden relations between documents.

  • The Postdoc aims to investigate different techniques for discovering the topics that occur in a collection of documents, and then to expand the query by using Automatic Query Expansion. The approach should consider five aspects:
    • Exploring the use of advanced Semantic Web tools to problems in Information Retrieval (IR).
    • Investigating approaches to discover the abstract “topics” that occur in a collection of documents based on topic model approaches and then expand the query to explore and discover hidden relations between the documents.
    • Demonstrating that classifying the corpus with meaningful descriptive information using topic modeling techniques can improve the results of IR methods.
    • Combining topic model and query expansion and apply to corpus documents.
    • Identifying personalized search results generation and hence improve the relatedness of the research results using topic modeling techniques together with topic-driven based community detection methods.
  • The postdoc is required to provide support to ongoing PhD student projects, and activities that evolve around the same research area.
  • The postdoc will be also involved in small load teaching activities related to Computer Science subjects.

REQUIREMENTS:

  • The candidate should hold a PhD in Computer Science. His/her work should be related to ontology learning and topic modeling techniques.
  • Proven experience in Knowledge representation, document classification, Topic modeling algorithms and Topic extraction. 
  • Excellent scripting and coding skills.
  • Excellent Communication skills.
  • Autonomous and team working capabilities.

OFFER DETAILS:

  • The postdoc will have the opportunity to work in a research group that gathers academic, and industrial partners. This environment allows the postdoc to participate in research gatherings, conferences, and visiting/working in different environments (e.g., in a research lab, partner institutions, and companies).
  • Contract duration: 12 months (with a contract extension possibility).
  • Gross Salary: 2300-2600 euros/month (depending on the candidate’s profile)
  • Main host institution: LIUPPA/OpenCEMS research group.

APPLICATION INSTRUCTIONS:

Please send your applications (in PDF format) to the following contacts: [email protected]The application (written in English) should include:

  • A Curriculum Vitae (including your contact address, work experience, publications, software repositories)
  • A cover letter
  • Two recommendation letters
  • Two of your best publications/implementations

Deadline for applications: June 25th 2022.Start date: September 1st, 2022 (negotiable). Screening of applications starts immediately and will continue until a candidate is selected. Therefore, early applications are encouraged.

REFERENCES:

  1. Anis Tissaoui, et al., A Top-down Enriching Approach for Ontology Learning From Text. Concurrency and Computation: Practice and Experience Journal – 2021. doi: 10.1002/cpe.7036
  2. Anis Tissaoui, et al., Probabilistic Topic Models for Enriching Ontology from Texts. SN COMPUT. SCI. 1, 336 (2020). doi: 10.1007/s42979-020-00349-y
  3. Ahmed Khemiri et al. (2021): Learn2Construct: An automatic ontology construction based on LDA from texual data. 13th International ACM Conference on Management of Emergent Digital EcoSystems (MEDES’21). doi: 10.1145/3444757.3485110